How to Use the Tuputech Moderation MCP in LangChain

Q: What if I need to correct a moderation result? Does Tuputech Moderation support user feedback with LangChain?

Absolutely. The submitfeedback tool allows you to provide manual input. This helps improve the underlying AI models, making your next chain run even better.

Build complex safety chains with LangChain. Turn moderation checks into actionable steps for your agent.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Tuputech Moderation MCP to LangChain

Create your Vinkius account to connect Tuputech Moderation to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Tuputech Moderation with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chaining multiple content checks via MCP Server

You can build multi-step reasoning where the output of one check dictates the next action. For example, after running `scan_text_abuse`, your chain can decide it also needs to run `scan_image_porn` on any attached media. This sequential flow means you don't just get a list of scores; you get an actionable path. Your agent decides *which* tools fire and in what order, making the moderation process part of a larger decision-making pipeline.

Deepfake and AI content detection for LangChain

Need to know if media is real? The `scan_image_synthetic` tool detects if an image was generated by AI. You can link this result directly into your chain's logic—if the score is high, you flag the entire record immediately. It works just like any other check. Your agent treats it as a piece of data: 'Synthetic Score = 0.9'. That number then becomes an input for the next tool in the sequence.

Automated spam and ad filtering with MCP Server

Don't just rely on simple keyword matching. Use `scan_text_spam` to check entire blocks of text for hidden ads or junk content. This output tells your agent if the data is usable or if it needs rejection. It’s a fast, reliable gatekeeper function. You can run this tool early in your chain's process—it cuts out bad inputs before they waste resources on downstream processing.

Setup guide

Set up Tuputech Moderation MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Tuputech Moderation tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "tuputech-moderation-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Tuputech Moderation transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Tuputech. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Tuputech Moderation now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Tuputech Moderation MCP in LangChain

The MCP Server lets your agent call moderation tools as part of its reasoning cycle. Instead of just checking text, the agent can check text *and* images sequentially to make a final decision.

You should integrate moderation tools into your ReAct agents. This means the agent decides whether it needs to run `scan_text_politics` or another check based on what it's trying to accomplish.

Yes, the MCP Server supports audio and video analysis. You can run `scan_audio_stream` or `scan_video_stream`, treating those results just like any other data point in your chain.

Absolutely. The `submit_feedback` tool allows you to provide manual input. This helps improve the underlying AI models, making your next chain run even better.

This MCP Server handles several media formats, including text, images, audio streams, and video streams. It's a multi-modal check.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python